update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- accuracy
|
| 6 |
+
model-index:
|
| 7 |
+
- name: MiniLMv2-L6-H384-distilled-from-RoBERTa-Large-finetuned-wikitext103-mlm-multi-emails-hq-x2bs
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# MiniLMv2-L6-H384-distilled-from-RoBERTa-Large-finetuned-wikitext103-mlm-multi-emails-hq-x2bs
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [saghar/MiniLMv2-L6-H384-distilled-from-RoBERTa-Large-finetuned-wikitext103](https://huggingface.co/saghar/MiniLMv2-L6-H384-distilled-from-RoBERTa-Large-finetuned-wikitext103) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 2.0371
|
| 19 |
+
- Accuracy: 0.6450
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 0.0002
|
| 39 |
+
- train_batch_size: 16
|
| 40 |
+
- eval_batch_size: 2
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- gradient_accumulation_steps: 4
|
| 44 |
+
- total_train_batch_size: 64
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: cosine
|
| 47 |
+
- lr_scheduler_warmup_ratio: 0.05
|
| 48 |
+
- num_epochs: 16.0
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 54 |
+
| 3.2947 | 1.0 | 308 | 3.0832 | 0.5122 |
|
| 55 |
+
| 2.8727 | 2.0 | 616 | 2.6722 | 0.5662 |
|
| 56 |
+
| 2.6339 | 3.0 | 924 | 2.4797 | 0.5878 |
|
| 57 |
+
| 2.5053 | 4.0 | 1232 | 2.3833 | 0.6025 |
|
| 58 |
+
| 2.4531 | 5.0 | 1540 | 2.3085 | 0.6106 |
|
| 59 |
+
| 2.2852 | 6.0 | 1848 | 2.2451 | 0.6175 |
|
| 60 |
+
| 2.228 | 7.0 | 2156 | 2.1937 | 0.6244 |
|
| 61 |
+
| 2.2013 | 8.0 | 2464 | 2.1446 | 0.6310 |
|
| 62 |
+
| 2.1463 | 9.0 | 2772 | 2.1062 | 0.6357 |
|
| 63 |
+
| 2.0882 | 10.0 | 3080 | 2.0847 | 0.6370 |
|
| 64 |
+
| 2.1669 | 11.0 | 3388 | 2.0687 | 0.6399 |
|
| 65 |
+
| 2.0983 | 12.0 | 3696 | 2.0629 | 0.6423 |
|
| 66 |
+
| 2.1215 | 13.0 | 4004 | 2.0259 | 0.6476 |
|
| 67 |
+
| 2.1255 | 14.0 | 4312 | 2.0378 | 0.6461 |
|
| 68 |
+
| 2.1751 | 15.0 | 4620 | 2.0257 | 0.6458 |
|
| 69 |
+
| 1.9516 | 16.0 | 4928 | 2.0371 | 0.6450 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- Transformers 4.27.0.dev0
|
| 75 |
+
- Pytorch 2.0.0.dev20230212+cu118
|
| 76 |
+
- Datasets 2.9.0
|
| 77 |
+
- Tokenizers 0.13.2
|